Abstract
In recent years, an emerging research work in recommendation systems aimed at exploring users’ potential interaction preferences. However, most existing methods can only capture information about the user’s purchase (or click) history. To estimate users’ potential interaction preferences more accurately, it is necessary to consider auxiliary information when modeling user-item interactions. In this paper, a Light Cross-Attention Network (LCAN) is proposed. LCAN makes full use of existing information in three parts: 1) User-Item interaction graph. The interaction history is an important signal, and the user’s interaction preferences can be obtained directly from the interaction history. 2) User-User and Item-Item relationships. The user-user and item-item graphs are additionally constructed based on the similarity between users and items to alleviate data sparseness. 3) Complementarity between graphs. Information between different graphs is interrelated, and a graph-level cross-attention network is used to capture the complementarity between graphs. Extensive experiments have been conducted by comparing state-of-the-art methods, and it shows that our LCAN model can outperform the most advanced recommendation methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
van den Berg, R., Kipf, T.N., Welling, M.: Graph convolutional matrix completion. CoRR abs/1706.02263 (2017)
Chen, L., Wu, L., Hong, R., Zhang, K., Wang, M.: Revisiting graph based collaborative filtering: a linear residual graph convolutional network approach. In: AAAI 2020, pp. 27–34. AAAI Press (2020)
Cheng, Z., Ding, Y., Zhu, L., Kankanhalli, M.S.: Aspect-aware latent factor model: rating prediction with ratings and reviews. In: WWW 2018, Lyon, France, 23–27 April 2018, pp. 639–648. ACM (2018)
He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., Wang, M.: LightGCN: simplifying and powering graph convolution network for recommendation. In: SIGIR, pp. 639–648. ACM (2020)
Jorro-Aragoneses, J.L., Díaz-Agudo, B., Recio-García, J.A., Jiménez-Díaz, G.: RecoLibry suite: a set of intelligent tools for the development of recommender systems. Autom. Softw. Eng. 27(1), 63–89 (2020)
Koren, Y., Bell, R.M., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42(8), 30–37 (2009)
Salakhutdinov, R., Mnih, A.: Probabilistic matrix factorization. In: Advances in Neural Information Processing Systems 20, pp. 1257–1264. Curran Associates, Inc. (2007)
Sedhain, S., Menon, A.K., Sanner, S., **e, L.: AutoRec: autoencoders meet collaborative filtering. In: WWW 2015, pp. 111–112. ACM (2015)
Sun, J., et al.: Neighbor interaction aware graph convolution networks for recommendation. In: SIGIR 2020, pp. 1289–1298. ACM (2020)
Wang, X., He, X., Wang, M., Feng, F., Chua, T.: Neural graph collaborative filtering. In: SIGIR 2019, pp. 165–174. ACM (2019)
Wang, X., **, H., Zhang, A., He, X., Xu, T., Chua, T.: Disentangled graph collaborative filtering. In: SIGIR 2020, pp. 1001–1010. ACM (2020)
Wang, X., Wang, R., Shi, C., Song, G., Li, Q.: Multi-component graph convolutional collaborative filtering. In: AAAI 2020, pp. 6267–6274. AAAI Press (2020)
Xu, Z., et al.: When recommender systems meet fleet management: practical study in online driver repositioning system. In: Huang, Y., King, I., Liu, T., van Steen, M. (eds.) WWW 2020, pp. 2220–2229. ACM/IW3C2 (2020)
Xue, H., Dai, X., Zhang, J., Huang, S., Chen, J.: Deep matrix factorization models for recommender systems. In: IJCAI 2017, pp. 3203–3209. ijcai.org (2017)
Zhang, Y., et al.: Towards poisoning the neural collaborative filtering-based recommender systems. In: Chen, L., Li, N., Liang, K., Schneider, S. (eds.) ESORICS 2020. LNCS, vol. 12308, pp. 461–479. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58951-6_23
Zhou, J., et al.: Graph neural networks: a review of methods and applications. AI Open 1, 57–81 (2020)
Zhu, H., et al.: Bilinear graph neural network with neighbor interactions. In: IJCAI 2020, pp. 1452–1458. ijcai.org (2020)
Acknowledgements
This work is supported by National Natural Science Foundation of China (Grant No. 62072060, 72074036), this work is also partly supported by the China Postdoctoral Science Foundation (2020M673145) and Program for Innovation Research Groups at Institutions of Higher Education in Chongqing (CXQT21032).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, L., Zhou, W., Wen, J., Zhang, Y., Wang, Y., Zhang, H. (2022). LCAN: Light Cross-Attention Network for Collaborative Filtering Recommendation. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2022. Lecture Notes in Computer Science(), vol 13280. Springer, Cham. https://doi.org/10.1007/978-3-031-05933-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-05933-9_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05932-2
Online ISBN: 978-3-031-05933-9
eBook Packages: Computer ScienceComputer Science (R0)